Data preprocessing techniques for classification without discrimination

F. Kamiran, T.G.K. Calders

    Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

    765 Citaten (Scopus)
    1 Downloads (Pure)

    Samenvatting

    Recently, the following Discrimination-Aware Classification Problem was introduced: Suppose we are given training data that exhibit unlawful discrimination; e.g., toward sensitive attributes such as gender or ethnicity. The task is to learn a classifier that optimizes accuracy, but does not have this discrimination in its predictions on test data. This problem is relevant in many settings, such as when the data are generated by a biased decision process or when the sensitive attribute serves as a proxy for unobserved features. In this paper, we concentrate on the case with only one binary sensitive attribute and a two-class classification problem. We first study the theoretically optimal trade-off between accuracy and non-discrimination for pure classifiers. Then, we look at algorithmic solutions that preprocess the data to remove discrimination before a classifier is learned. We survey and extend our existing data preprocessing techniques, being suppression of the sensitive attribute, massaging the dataset by changing class labels, and reweighing or resampling the data to remove discrimination without relabeling instances. These preprocessing techniques have been implemented in a modified version of Weka and we present the results of experiments on real-life data. Keywords: Classification – Preprocessing – Discrimination-aware data mining
    Originele taal-2Engels
    Pagina's (van-tot)1-33
    TijdschriftKnowledge and Information Systems
    Volume33
    Nummer van het tijdschrift1
    DOI's
    StatusGepubliceerd - 2012

    Vingerafdruk

    Duik in de onderzoeksthema's van 'Data preprocessing techniques for classification without discrimination'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit